W 4 A1 | Ex- 8 | Assertion Error: Not all tests were passed for Linear_activation_forward

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

I have the following error when trying to build the linear_activation_backward() function. I am not sure what input to assign to my function. Can someone point me towards the right direction. Thank you!

image
image1215×499 22.6 KB

2

That is not much information to go on. What output values to do get for the earlier print statements in that test cell? Do your values agree with the “Expected values” as shown below or not? Please show us what you get.

3

Hi,
Thank you for your reply.It works now for me.Earlier, I used the mathematical formular for the relu/sigmoid_backward instead of calling the function directly.
Calling the function directly solved the problem

4

In my case the error was that I copied this:

  • sigmoid_backward: Implements the backward propagation for SIGMOID unit. You can call it as follows:
dZ = sigmoid_backward(dA, activation_cache)
  • relu_backward: Implements the backward propagation for RELU unit. You can call it as follows:
dZ = relu_backward(dA, activation_cache)

In the same order into the source code but in the source code the order deviates which is a intricacy that when missed can throw an error.

5

Hey, Sahin.

You’ve copied-pasted those codes for dZ, but to get the real idea, we need the error log. Please show us the traceback/error log that you are receiving.